memory_stats
AI agents call memory_stats to retrieve information from Hippocampus Memory MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Stats retrieval is a read operation—it queries information about the memory system without modifying, deleting, or executing external operations. The low severity reflects that memory statistics alone pose minimal risk even if misused by an agent. Confidence is moderate (0.85) because the description is empty, requiring inference from context and naming conventions.
From the tool's definition Tool name 'memory_stats' with sibling tools including 'memory_read', 'memory_write', 'memory_consolidate', and 'memory_forget' suggests this retrieves statistics or metadata about memory storage.
Attacks that exploit this kind of access
memory_stats. It is categorised as a Read tool in the Hippocampus Memory MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Hippocampus Memory MCP Server MCP server in PolicyLayer and add a rule for memory_stats: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Hippocampus Memory MCP Server. Nothing to install.
memory_stats is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the memory_stats rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for memory_stats. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
memory_stats is provided by the Hippocampus Memory MCP Server MCP server (jameslovespancakes/memory-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →